GuidedStyle: Attribute knowledge guided style manipulation for semantic face editing

Hou, Xianxu; Zhang, Xiaokang; Liang, Hanbang; Shen, Linlin; Lai, Zhihui; Wan, Jun

doi:10.1016/j.neunet.2021.10.017

Cited by 52 publications

(37 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various works have demonstrated that editing images via non-linear latent paths typically results in more faithful, disentangled edits [4,27]. Following these works, we now explore learning non-linear latent editing paths within the W+ latent space using the StyleCLIP mapper technique [48].…”

Section: Editing Via Non-linear Latent Pathsmentioning

confidence: 99%

Third Time's the Charm? Image and Video Editing with StyleGAN3

Alaluf¹,

Patashnik²,

Wu³

et al. 2022

Preprint

View full text Add to dashboard Cite

StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this work, we explore the recent StyleGAN3 architecture, compare it to its predecessor, and investigate its unique advantages, as well as drawbacks. In particular, we demonstrate that while StyleGAN3 can be trained on unaligned data, one can still use aligned data for training, without hindering the ability to generate unaligned imagery. Next, our analysis of the disentanglement of the different latent spaces of StyleGAN3 indicates that the commonly used W/W+ spaces are more entangled than their StyleGAN2 counterparts, underscoring the benefits of using the StyleSpace for fine-grained editing. Considering image inversion, we observe that existing encoder-based techniques struggle when trained on unaligned data. We therefore propose an encoding scheme trained solely on aligned data, yet can still invert unaligned images. Finally, we introduce a novel video inversion and editing workflow that leverages the capabilities of a fine-tuned Style-GAN3 generator to reduce texture sticking and expand the field of view of the edited video. Code is available on our project page: https://yuval-alaluf.github.io/ stylegan3-editing/.* Denotes equal contribution.

show abstract

Section: Editing Via Non-linear Latent Pathsmentioning

confidence: 99%

Third Time's the Charm? Image and Video Editing with StyleGAN3

Alaluf¹,

Patashnik²,

Wu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Most notably, the discovery of such interpretable directions have received much research attention with the advancement of StyleGAN. Recent works have sought to identify a semantically meaningful path in a supervised manner, which requires a large number of annotated images [2] or attribute predictors on the predefined semantics [17,36].…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, these works typically require manual tuning of hyperparameters such as manipulation strength and disentanglement magnitude. Other works take an alternative approach and train a network that predicts a per-image offset in the latent space for an intended edit [2,3,17,29]. These methods neither assume perfect disentanglement in the latent space, nor require manual tuning of the edit magnitude.…”

Section: Introductionmentioning

confidence: 99%

FEAT: Face Editing with Attention

Hou¹,

Shen²,

Patashnik³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…As may be expected, non-linear approaches can present higher quality editing at the cost of simplicity. Hou et al [2022], operate similarly to Yang et al [2020a] by using classifiers. However, they propose to move beyond global, linear directions and towards a non-linear traversal paradigm.…”

Section: Latent Space Editingmentioning

confidence: 99%

State-of-the-Art in the Architecture, Methods and Applications of StyleGAN

Bermano¹,

Gal²,

Alaluf³

et al. 2022

Preprint

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have established themselves as a prevalent approach to image synthesis. Of these, StyleGAN offers a fascinating case study, owing to its remarkable visual quality and an ability to support a large array of downstream tasks. This state-of-the-art report covers the StyleGAN architecture, and the ways it has been employed since its conception, while also analyzing its severe limitations. It aims to be of use for both newcomers, who wish to get a grasp of the field, and for more experienced readers that might benefit from seeing current research trends and existing tools laid out. Among StyleGAN's most interesting aspects is its learned latent space. Despite being learned with no supervision, it is surprisingly well-behaved and remarkably disentangled. Combined with StyleGAN's visual quality, these properties gave rise to unparalleled editing capabilities. However, the control offered by StyleGAN is inherently limited to the generator's learned distribution, and can only be applied to images generated by StyleGAN itself. Seeking to bring StyleGAN's latent control to real-world scenarios, the study of GAN inversion and latent space embedding has quickly gained in popularity. Meanwhile, this same study has helped shed light on the inner workings and limitations of StyleGAN. We map out StyleGAN's impressive story through these investigations, and discuss the details that have made StyleGAN the go-to generator. We further elaborate on the visual priors StyleGAN constructs, and discuss their use in downstream discriminative tasks. Looking forward, we point out StyleGAN's limitations and speculate on current trends and promising directions for future research, such as task and target specific fine-tuning.

show abstract

GuidedStyle: Attribute knowledge guided style manipulation for semantic face editing

Cited by 52 publications

References 12 publications

Third Time's the Charm? Image and Video Editing with StyleGAN3

Third Time's the Charm? Image and Video Editing with StyleGAN3

FEAT: Face Editing with Attention

State-of-the-Art in the Architecture, Methods and Applications of StyleGAN

Contact Info

Product

Resources

About